competitive-intelligence-spider
Pass
Audited by Gen Agent Trust Hub on Mar 25, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill functions by fetching and processing content from external websites, which creates an inherent surface for indirect prompt injection.
- Ingestion points: The skill retrieves data from competitor URLs specified by the user in the configuration.
- Boundary markers: No specific delimiters or safety instructions are defined to isolate the external web content from the agent's core instructions.
- Capability inventory: Uses the WebFetch tool for data collection and generates summaries for reporting; it does not request access to sensitive local files or administrative privileges.
- Sanitization: The fetched content is processed directly for analysis without specified filtering or sanitization steps.
- [NO_CODE]: The skill consists entirely of markdown documentation and templates and does not contain any executable scripts, binaries, or automated installation commands.
- [SAFE]: The analysis detected no malicious patterns, such as command execution, data exfiltration of sensitive files, or persistence mechanisms. The behavior is entirely consistent with the skill's stated purpose of competitive analysis.
Audit Metadata